Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2320 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1873. Min Range: -5.1873
Max Act: 5.1873. Min Act: -0.1700
Data Index: 1506712 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.9061. Min Act: -0.1700
Data Index: 2969441 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.9373. Min Act: -0.1700
Data Index: 8095550 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.8436. Min Act: -0.1700
Data Index: 460001 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.7498. Min Act: -0.1700
Data Index: 2517633 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.7186. Min Act: -0.1700
Data Index: 63879 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.6873. Min Act: -0.1700
Data Index: 6827614 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.6873. Min Act: -0.1700
Data Index: 6987347 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.6561. Min Act: -0.1700
Data Index: 2304674 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.6248. Min Act: -0.1700
Data Index: 4397920 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.6248. Min Act: -0.1700
Data Index: 4806 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.5936. Min Act: -0.1700
Data Index: 3662394 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.6248. Min Act: -0.1700
Data Index: 321655 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.5936. Min Act: -0.1700
Data Index: 3347741 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.5311. Min Act: -0.1700
Data Index: 789302 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.5311. Min Act: -0.1700
Data Index: 6454761 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.5311. Min Act: -0.1700
Data Index: 3243520 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.4998. Min Act: -0.1700
Data Index: 5911617 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.5311. Min Act: -0.1700
Data Index: 4876745 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1873. Min Range: -5.1873
Max Act: 4.5311. Min Act: -0.1700
Data Index: 288987 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19